c-research
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from various external sources, making it vulnerable to indirect prompt injection. Malicious instructions within summarized content could be used to manipulate the agent's behavior.
- Ingestion points: Web URLs, PDF files, YouTube videos, and podcast feeds referenced in SKILL.md.
- Boundary markers: No delimiters or instructions are used to separate user data from system instructions.
- Capability inventory: Execution of the 'summarize' CLI tool (SKILL.md).
- Sanitization: There is no evidence of data sanitization or filtering.
- [COMMAND_EXECUTION]: The skill directs the agent to execute a CLI tool with absolute file paths (SKILL.md), which could be exploited to access and expose sensitive local system files if the agent has sufficient permissions.
Audit Metadata